Publications

228 results for Adversarial Robustness and Privacy

PEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networks
- - Huzaifa Arif
  - Keerthiram Murugesan
  - et al.
- 2025
- IEEE SaTML 2025
Conference paper
VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis
- - Chia-Yi Hsu
  - Jia-You Chen
  - et al.
- 2025
- ICASSP 2025
Conference paper
Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation
- - Maya Anderson
  - Guy Amit
  - et al.
- 2025
- ICISSP 2025
Short paper
The inherent adversarial robustness of analog in-memory computing
- - Corey Lammie
  - Julian Büchel
  - et al.
- 2025
- Nature Communications
Paper
Exploring Research and Tools in AI Security: A Systematic Mapping Study
- - Sidhant Narula
  - Mohammad Ghasemigol
  - et al.
- 2025
- IEEE Access
Paper
Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
- - Kristjan Greenewald
  - Yuancheng Yu
  - et al.
- 2024
- NeurIPS 2024
Conference paper
Unified Lookup Tables: Privacy-Preserving Foundation Models
- - Nikita Janakarajan
  - Irina Espejo Morales
  - et al.
- 2024
- NeurIPS 2024
Workshop paper
Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
- - Ambrish Rawat
  - Stefan Schoepf
  - et al.
- 2024
- NeurIPS 2024
Workshop
Membership Inference Attacks Against Time-Series Models
- - Noam Koren
  - Abigail Goldsteen
  - et al.
- 2024
- ACML 2024
Conference paper
MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
- - Giandomenico Cornacchia
  - Kieran Fraser
  - et al.
- 2024
- AIES 2024
Poster